Vaishnavh Nagarajan

About Me


6105 Gates Hillman Center, Carnegie Mellon University

I am a third year PhD student in the Computer Science Department of Carnegie Mellon University (CMU). I am fortunate to be advised by Zico Kolter. My interests lie in the algorithmic and foundational aspects of Machine Learning and Artificial Intelligence. Currently I am working on theoretically understanding Generative Adversarial Networks and Deep Learning. In the past I have worked in Learning Theory, Multi-Agent Systems and Reinforcement Learning.

I completed my undergraduate studies in the Department of Computer Science and Engineering at the Indian Institute of Technology, Chennai, India. Here I was advised by Balaraman Ravindran with whom I worked in Reinforcement Learning.

Here is a link to my CV.


Full Conference Papers

  • Gradient descent GAN optimization is locally stable, Neural Information Processing Systems (NIPS) 2017 (Accepted for Oral presentation)
    Vaishnavh Nagarajan and J. Zico Kolter
    [arxiv] [1hr talk - slides] [NIPS Oral - Slides] [Poster] [3 min video]

  • Lifelong Learning in Costly Feature Spaces, Algorithmic Learning Theory (ALT) 2017
    with Maria-Florina Balcan and Avrim Blum

  • Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems, Conference On Learning Theory (COLT), 2017
    with Maria-Florina Balcan, Ellen Vitercik and Colin White
    [arxiv] [Slides] [Talk]

  • Every team deserves a second chance: Identifying when things go wrong, Autonomous Agents and Multiagent Systems (AAMAS) 2015
    (Double 1st author) Vaishnavh Nagarajan, Leandro S. Marcolino and Milind Tambe
    [PDF] [Appendix]

Workshop Papers

  • Generalization in Deep Networks: The Role of Distance from Initialization, Neural Information Processing Systems (NIPS) 2017 - Deep Learning: Bridging Theory and Practice (Accepted for Spotlight talk)
    Vaishnavh Nagarajan and J. Zico Kolter.

  • A Reinforcement Learning Approach to Online Learning of Decision Trees, European Workshop on Reinforcement Learning (EWRL 2015 - ICML)
    (Triple 1st author) Abhinav Garlapati, Aditi Raghunathan, Vaishnavh Nagarajan and Balaraman Ravindran.

Short Papers and Demonstrations

  • Knows-What-It-Knows Inverse Reinforcement Learning, Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2015
    Vaishnavh Nagarajan and Balaraman Ravindran

Last Updated: Apr 24th, 2018